Triple
T15476172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xiaoyoukeng fumarole area |
E376785
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object |
Lengshuikeng
Lengshuikeng is a geothermal area in Taiwan’s Yangmingshan National Park known for its hot springs, sulfur vents, and volcanic landscapes.
|
E1159366
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Lengshuikeng | Statement: [Xiaoyoukeng fumarole area, near, Lengshuikeng]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lengshuikeng Context triple: [Xiaoyoukeng fumarole area, near, Lengshuikeng]
-
A.
Fengjing
Fengjing is an ancient water town in Shanghai, China, renowned for its well-preserved traditional architecture, stone bridges, and network of canals.
-
B.
West Liulichang
West Liulichang is the western portion of Beijing’s historic Liulichang cultural street, known for its traditional shops selling antiques, calligraphy, paintings, and rare books.
-
C.
Wuping
Wuping was an era name used during the Northern Qi dynasty in imperial China, marking a specific reign period within that dynasty’s rule.
-
D.
Yongcong
Yongcong was a Qing dynasty imperial prince, one of the sons of the Qianlong Emperor of China.
-
E.
Xiping
Xiping was an era name used during the reign of Emperor Ling in the late Eastern Han dynasty of China.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lengshuikeng Triple: [Xiaoyoukeng fumarole area, near, Lengshuikeng]
Generated description
Lengshuikeng is a geothermal area in Taiwan’s Yangmingshan National Park known for its hot springs, sulfur vents, and volcanic landscapes.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lengshuikeng Target entity description: Lengshuikeng is a geothermal area in Taiwan’s Yangmingshan National Park known for its hot springs, sulfur vents, and volcanic landscapes.
-
A.
Fengjing
Fengjing is an ancient water town in Shanghai, China, renowned for its well-preserved traditional architecture, stone bridges, and network of canals.
-
B.
West Liulichang
West Liulichang is the western portion of Beijing’s historic Liulichang cultural street, known for its traditional shops selling antiques, calligraphy, paintings, and rare books.
-
C.
Wuping
Wuping was an era name used during the Northern Qi dynasty in imperial China, marking a specific reign period within that dynasty’s rule.
-
D.
Yongcong
Yongcong was a Qing dynasty imperial prince, one of the sons of the Qianlong Emperor of China.
-
E.
Xiping
Xiping was an era name used during the reign of Emperor Ling in the late Eastern Han dynasty of China.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d85cd21dcc81908646251b1c26ea00 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f88a5dc8190a2d7830748e29180 |
completed | April 16, 2026, 1:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff2d093ccc8190aefc355a837c83f4 |
completed | May 9, 2026, 12:48 p.m. |
| NEDg | Description generation | batch_69ff3015ee2c8190ad2c28cd2850d903 |
completed | May 9, 2026, 1:01 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff30ed9a5481909cefad0ef877a2e9 |
completed | May 9, 2026, 1:04 p.m. |
Created at: April 10, 2026, 3:34 a.m.